Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mixer
    -0.07
    ую
    -0.06
     Vlad
    -0.06
     pinch
    -0.06
     민
    -0.06
    Barcode
    -0.06
     BBQ
    -0.06
     Wild
    -0.06
    ěst
    -0.06
    /Public
    -0.06
    POSITIVE LOGITS
     sharedInstance
    0.07
     incontri
    0.07
     davranış
    0.07
     вигляді
    0.07
    /Add
    0.06
     incarn
    0.06
     fantas
    0.06
     하
    0.06
     мг
    0.06
     보
    0.06
    Act Density 0.005%

    No Known Activations